Security audit
Security checks for vulnerabilities and agentic risk
This skill provides a disclosed workflow for turning report-like Markdown into self-contained HTML and does not show hidden execution, credential access, network retrieval, or persistence.
Install this when you want a Chinese-language workflow for transforming long reports into standalone HTML pages. Review generated HTML before sharing, especially if the source report contains confidential or regulated information, because the skill is designed to preserve and re-present the report's facts.
The trigger description is very broad and includes many common user phrasings such as converting reports to HTML, beautifying reports, or making pages easier to share. This can cause the skill to activate outside its intended scope, leading the agent to rewrite or transform content when the user may only want simple formatting or a different kind of assistance.
L03 的整体描述仅以中文规定技能用途和行为，未说明是否支持用户按偏好选择输出语言；若该技能在更广泛环境中使用，可能构成默认强制特定语言/locale 的自然语言策略问题。文件中也未见这是面向特定中文区域用户的明确限定或用户可选项。
The entire instruction file is written as mandatory guidance in Chinese, and it also includes language-specific requirements such as Chinese font fallbacks for body text. There is no indication that the user can opt into another language or locale, which may violate a language/locale choice policy.
The entire skill file is written in Chinese and provides all instructions, labels, and required output formats only in Chinese. There is no indication that the skill is region-specific, no opt-in for language preference, and no alternative locale guidance, which can violate language/locale policy requirements.
The entire skill reference is written as a mandatory instruction set in Chinese, with imperative requirements such as '没有契约，不写 HTML' and no indication that users may choose another language or locale. Under the policy, forcing a specific language without offering user choice is a natural-language policy violation.
This markdown file contains user-facing review instructions exclusively in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule for natural-language violations, forcing a specific language without opt-in is a reportable issue.
No suspicious patterns detected.
